Clustering ensembles of social networks

2019 ◽  
Vol 7 (2) ◽  
pp. 141-159
Author(s):  
Tracy M. Sweet ◽  
Abby Flynt ◽  
David Choi
Keyword(s):  
Social Sciences ◽  
Social Networks ◽  
Data Structures ◽  
Network Data ◽  
Advice Seeking ◽  
Clustering Ensembles ◽  
The Social ◽  
Simulated Network ◽  
Class Labels

AbstractRecently there has been significant work in the social sciences involving ensembles of social networks, that is, multiple, independent, social networks such as students within schools or employees within organizations. There remains, however, very little methodological work on exploring these types of data structures. We present methods for clustering social networks with observed nodal class labels, based on statistics of walk counts between the nodal classes. We extend this method to consider only non-backtracking walks, and introduce a method for normalizing the counts of long walk sequences using those of shorter ones. We then present a method for clustering networks based on these statistics to explore similarities among networks. We demonstrate the utility of this method on simulated network data, as well as on advice-seeking networks in education.

scholarly journals Measuring educational segregation using a whole population network of the Netherlands

2021 ◽  
Author(s):  
Jan van der Laan ◽  
Marjolijn Das ◽  
Saskia te Riele ◽  
Edwin de Jonge ◽  
Tom Emery
Keyword(s):  
Social Sciences ◽  
Social Networks ◽  
Random Walk ◽  
The Netherlands ◽  
Network Science ◽  
Extended Family ◽  
Educational Institution ◽  
Educational Backgrounds ◽  
The Social ◽  
New Applications

In this analysis we present a whole population network which uses administrative data to construct a network incorporating 1.4 billion relationships between the 17 million inhabitants of the Netherlands. Relationships are identified between individuals who live in the same household, live close to each other, work for the same company, attend the same educational institution, or belong to the same extended family. This network has properties that are rare in observed social networks, which opens up new applications for network science in the social sciences. To demonstrate the applications of such a network, we use a random walk approach to estimate segregation of individuals from differing educational backgrounds and whether specific types of relationships increase or decrease this segregation. The results suggest that relationships between people in the same household greatly increase segregation whilst work, school and neighborhood networks relationships increase exposure to individuals with different backgrounds. The size of these effects is context dependent. Further applications of a whole population network are also discussed

scholarly journals Privacy Preservation in Sequential Published Social Networks Against Mutual Friend Attack

2018 ◽  
Vol 7 (4) ◽  
pp. 3731
Author(s):  
Jyothi Vadisala ◽  
Valli Kumari Vatsavayi
Keyword(s):  
Social Networks ◽  
Privacy Preservation ◽  
Dynamic Networks ◽  
Third Party ◽  
Published Data ◽  
Network Data ◽  
Time Interval ◽  
Dynamic Social Networks ◽  
The Social ◽  
Mutual Friend

In recent years the social networks are widely used the way of connecting people, interact with each other and share the information. The social network data is rich in content and the data are published for third party users such as researchers. The social interaction between individual’s changes rapidly as time changes so there is a need of privacy preserving in dynamic networks. An adversary can acquire some local knowledge about individuals in the network and can easily breach the privacy of a few victims. This paper mainly focuses on preserving privacy in sequential published network data where the adversary has some knowledge about the number of mutual friends of the target victims over a time period. The kw-Number of Mutual Friend Anonymization model is proposed to anonymize each sequential published network. In this privacy model, k indicates the privacy level and w is the time interval taken by the adversary to acquire the knowledge of the victim. By this approach the adversary cannot identify the victim by acquiring the knowledge of each sequential published data. The performance evaluation shows that the proposed approach can preserve many characteristics of the dynamic social networks.

scholarly journals Turismo y bitters en Argentina. Riesgos y potencialidades emergentes de la discusión sobre la Fernet Fest 2012

STUDIUM ◽  
2019 ◽  
pp. 197-216
Author(s):  
Martín Eynard
Keyword(s):  
Social Sciences ◽  
Social Networks ◽  
Redes Sociales ◽  
Virtual Ethnography ◽  
The Social ◽  
The World ◽  
Alcoholic Drinks ◽  
Sociedad Civil ◽  
Main Components ◽  
Medios De Comunicacion

Argentina es el país que mayores volúmenes de fernetconsume en el mundo. En el 2012 se intentó llevar a cabo en Mendiolaza (Provincia de Córdoba, Argentina), un festival popular alrededor del fernet, para romper un record Guinness. Sin embargo, una disputa que se inició entre diversos actores (sociedad civil, gobiernos y empresa) terminaría sepultando laFernet Fest. Pese a no realizarse dicho evento, los debates expresados a través de distintos medios de comunicación en aquel contexto enriquecieron, desde las ciencias sociales, las distintas aristas de la discusión en torno a la gastronomía y el turismo. El objetivo de este trabajo fue analizar los emergentes que surgieron en torno al mencionado debate en el marco de la eventual realización de la Fernet Fest. Metodológicamente, se utilizó etnografía virtual para el análisis de artículos de diversos medios gráficos, como así también de sitios de internet y redes sociales. A través del análisis de las diversas voces, fue posible delinear los principales argumentos que surgieron a favor y en contra de la realización del festival, que consideramos son importantes a la hora de pensar sobre las festividades vinculadas al turismo que tienen como componentes centrales las bebidas alcohólicas. Palabras claves:turismo, gastronomía, festividades, fernet,Argentina   Argentina is the country that consumes the largest volumes of fernet in the world. In 2012, a popular festival around fernet was attempted in Mendiolaza (Province of Córdoba, Argentina) to break a Guinness record. However, a dispute that began between various actors (civil society, governments and company) would end up burying the Fernet Fest. In spite of not having said event, the debates expressed through different press in that context enriched, from the social sciences, the different edges of the discussion around gastronomy and tourism. The objective of this work was to analyze the emerging arguments that arose around the mentioned debate in the framework of the eventual realization of the Fernet Fest. Methodologically, virtual ethnography was used to analyze articles from various newspapers, as well as from internet sites and social networks. Through the analysis of the different voices, it was possible to delineate the main arguments that arose in favor and against the realization of the festival, which we consider important when thinking about the festivities linked to tourism, whose main components are alcoholic drinks. Key words:tourism, gastronomy, festivities, fernet, Argentina

An Exploratory Theoretical Framework for Understanding Information Behaviour

2013 ◽  
pp. 1-8
Author(s):  
Osemeke Mosindi ◽  
Petia Sice
Keyword(s):  
Social Sciences ◽  
Social Networks ◽  
Complexity Theory ◽  
Information Behaviour ◽  
Direct Benefits ◽  
The Social ◽  
Individual Actor ◽  
Recent Trends ◽  
The Individual ◽  
The Impact

Recent trends in researching Information Behaviour in organisations show that the initial focus on technology has shifted to cognitive methods that take the individual into account, but more recently there has been a move to the social sciences approach. Literature shows that this approach has been informative but rather theoretic as there has been limited work using this approach to handle information problems in organisations. There is a need to develop and test theories to help understand Information Behaviour in organisations in a social science context that gives direct benefits to the organisation. It is useful to view organisations as complex social networks of interactions, where importance is put on the relationships between people in the organisations, as well as on the individual actor. A need exists to evaluate and connect insights from social sciences communities of practice, and complexity theory. This paper explores insights from these theories and develops a conceptual framework for understanding Information Behaviour in organisations. Data collection is in a preliminary stage, reflections and observations, of the researcher and a few participants. The intention is to provoke thoughts along the lines of seeking to use a synergy between theories that can offer different and useful platforms to help better understand the impact of information behaviour on organizational culture.

Mining of Leaders in Mobile Telecom Social Networks

2016 ◽  
pp. 68-77
Author(s):  
Mantian (Mandy) Hu
Keyword(s):  
Social Networks ◽  
Big Data ◽  
Social Network ◽  
Information Diffusion ◽  
Network Data ◽  
Massive Datasets ◽  
Social Network Data ◽  
The Social ◽  
Marketing Efficiency ◽  
Mobile Telecom

In the age of Big Data, the social network data collected by telecom operators are growing exponentially. How to exploit these data and mine value from them is an important issue. In this article, an accurate marketing strategy based on social network is proposed. The strategy intends to help telecom operators to improve their marketing efficiency. This method is based on mutual peers' influence in social network, by identifying the influential users (leaders). These users can promote the information diffusion prominently. A precise marketing is realized by taking advantage of the user's influence. Data were collected from China Mobile and analyzed. For the massive datasets, the Apache Spark was chosen for its good scalability, effectiveness and efficiency. The result shows a great increase of the telecom traffic, compared with the result without leader identification.

Keyword Based Searching in Social Networks

2017 ◽  
Vol 2 (2) ◽  
pp. 60
Author(s):  
Zainab Nayyar ◽  
Nousheen Hashmi ◽  
Nazish Rafique ◽  
Khurram Mahmood
Keyword(s):  
Social Networks ◽  
Social Network ◽  
The Political ◽  
Network Data ◽  
Social Network Data ◽  
Research Article ◽  
The Social

The main purpose of analyzing the social network data is to observe the behaviors and trends that are followed by people. How people interact with each other, what they usually share, what are their interests on social networks, so that analysts can focus on new trends for the provision of those aspects which are of great interest for people so in this research article an easy approach of gathering and analyzing data through keyword based search in social networks is examined using NodeXL and data is gathered from twitter in which political trends have been analyzed. As a result the political trends among people are analyzed.

scholarly journals Analysis of large-scale social and information networks

2013 ◽  
Vol 371 (1987) ◽  
pp. 20120378 ◽  
Author(s):  
Jon Kleinberg
Keyword(s):  
Social Sciences ◽  
Social Networks ◽  
Social Interaction ◽  
Large Scale ◽  
Information Networks ◽  
Social Feedback ◽  
Feedback Effects ◽  
The Social ◽  
Link Information ◽  
The Web

The growth of the Web has required us to think about the design of information systems in which large-scale computational and social feedback effects are simultaneously at work. At the same time, the data generated by Web-scale systems—recording the ways in which millions of participants create content, link information, form groups and communicate with one another—have made it possible to evaluate long-standing theories of social interaction, and to formulate new theories based on what we observe. These developments have created a new level of interaction between computing and the social sciences, enriching the perspectives of both of these disciplines. We discuss some of the observations, theories and conclusions that have grown from the study of Web-scale social interaction, focusing on issues including the mechanisms by which people join groups, the ways in which different groups are linked together in social networks and the interplay of positive and negative interactions in these networks.

scholarly journals From temporal network data to the dynamics of social relationships

2021 ◽  
Vol 288 (1959) ◽  
Author(s):  
Valeria Gelardi ◽  
Didier Le Bail ◽  
Alain Barrat ◽  
Nicolas Claidiere
Keyword(s):  
Social Networks ◽  
Social Relationships ◽  
Social Evolution ◽  
Time Windows ◽  
Social Systems ◽  
Standard Technique ◽  
Dynamic Evolution ◽  
Network Data ◽  
Temporal Network ◽  
The Social

Networks are well-established representations of social systems, and temporal networks are widely used to study their dynamics. However, going from temporal network data (i.e. a stream of interactions between individuals) to a representation of the social group’s evolution remains a challenge. Indeed, the temporal network at any specific time contains only the interactions taking place at that time and aggregating on successive time-windows also has important limitations. Here, we present a new framework to study the dynamic evolution of social networks based on the idea that social relationships are interdependent: as the time we can invest in social relationships is limited, reinforcing a relationship with someone is done at the expense of our relationships with others. We implement this interdependence in a parsimonious two-parameter model and apply it to several human and non-human primates’ datasets to demonstrate that this model detects even small and short perturbations of the networks that cannot be detected using the standard technique of successive aggregated networks. Our model solves a long-standing problem by providing a simple and natural way to describe the dynamic evolution of social networks, with far-reaching consequences for the study of social networks and social evolution.

scholarly journals Actividad e involucramiento en torno a las cuentas de Twitter de periodistas y noticieros televisivos nacionales en México

2019 ◽  
Vol 9 (1) ◽  
pp. 33-56
Author(s):  
Antonio Corona ◽  
◽  
Brenda Azucena Muñoz ◽  
Keyword(s):  
Social Sciences ◽  
Qualitative Research ◽  
Social Networks ◽  
Quantitative Analysis ◽  
User Involvement ◽  
The Internet ◽  
Political Identities ◽  
Quantitative And Qualitative Research ◽  
Internet News ◽  
The Social

In the light of the growing divide between political identities on the internet, news distribution on social networks and the attitude of users towards said news has become a very important subject of study for the social sciences these past few years. This report presents the results of our analysis of formal news accounts activity on Twitter throughout 2017, as well as the interactions that surround them, arranged by account, type of activity and segment of interest. From these results, a few possible indicators are proposed for measuring user involvement, searching for an index that allows us to identify controversies in the discussion of news on Twitter. We conclude that the best way to measure involvement is by cross-graphing the amount of interactions per post and the proportion of retweets to formal interactions. This indicator could facilitate both quantitative and qualitative research on Twitter by identifying moments of high enunciation. Keywords: Participation; User Involvement; Twitter; Quantitative Analysis.

scholarly journals The Continued Relevance of Ego Network Data

2020 ◽  
pp. 169-187
Author(s):  
Jeffrey A. Smith
Keyword(s):  
Social Sciences ◽  
Data Sources ◽  
Statistical Techniques ◽  
Network Data ◽  
Personal Network ◽  
Network Information ◽  
The Social ◽  
Potential Applications ◽  
Basic Features ◽  
Full Network

Ego network data have a long history in the social sciences, acting as a bridge between traditional statistical techniques and network analysis. Ego network data provide personal network information, as the data are based on a sample of individuals. This chapter details the basic features of such data, describing the advantages, disadvantages, and potential applications of using ego network data. Ego network data remain a popular choice, despite the growing availability of full network data sources. This is in large part because ego network data are easy to collect but still provide a surprisingly large amount of network information. Ego network data are also quite flexible, with past work using the same basic data structure for widely different purposes. Given the ease of collection and the flexibility of use, there is every reason to believe that ego network data will continue to be a useful option for network scholars.

Sign in / Sign up

Export Citation Format

Share Document